Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to lines, geometry, and road markings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    lines or line segments

    np_acts-logits-general · gemini-2.0-flash

    lines and their geometric relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelRenderer
    -0.42
    TemporalType
    -0.41
     nahilalakip
    -0.40
     pouss
    -0.37
    XmlType
    -0.35
     GenerationType
    -0.35
    ModelForm
    -0.35
    WaitGroup
    -0.33
     Clo
    -0.33
     Clover
    -0.32
    POSITIVE LOGITS
     lines
    0.99
     Lines
    0.91
    lines
    0.86
     line
    0.84
     LINES
    0.82
     lijn
    0.81
     garis
    0.80
     Line
    0.79
    Lines
    0.77
     BorderSide
    0.75
    Act Density 0.966%

    No Known Activations